Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[ML] Include message in field_stats for text log files #34861

Merged
merged 2 commits into from
Oct 26, 2018
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
Expand Up @@ -89,6 +89,7 @@ static TextLogFileStructureFinder makeTextLogFileStructureFinder(List<String> ex
mappings.put(FileStructureUtils.DEFAULT_TIMESTAMP_FIELD, Collections.singletonMap(FileStructureUtils.MAPPING_TYPE_SETTING, "date"));

SortedMap<String, FieldStats> fieldStats = new TreeMap<>();
fieldStats.put("message", FileStructureUtils.calculateFieldStats(sampleMessages, timeoutChecker));

GrokPatternCreator grokPatternCreator = new GrokPatternCreator(explanation, sampleMessages, mappings, fieldStats, timeoutChecker);
// We can't parse directly into @timestamp using Grok, so parse to some other time field, which the date filter will then remove
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -7,11 +7,16 @@

import org.elasticsearch.common.collect.Tuple;
import org.elasticsearch.common.util.set.Sets;
import org.elasticsearch.xpack.core.ml.filestructurefinder.FieldStats;
import org.elasticsearch.xpack.core.ml.filestructurefinder.FileStructure;
import org.elasticsearch.xpack.ml.filestructurefinder.TimestampFormatFinder.TimestampMatch;

import java.util.Collections;
import java.util.Set;
import java.util.stream.Collectors;

import static org.hamcrest.Matchers.hasItem;
import static org.hamcrest.Matchers.not;

public class TextLogFileStructureFinderTests extends FileStructureTestCase {

Expand Down Expand Up @@ -127,6 +132,11 @@ public void testCreateConfigsGivenElasticsearchLog() throws Exception {
assertEquals("\\[%{TIMESTAMP_ISO8601:timestamp}\\]\\[%{LOGLEVEL:loglevel} \\]\\[.*", structure.getGrokPattern());
assertEquals("timestamp", structure.getTimestampField());
assertEquals(Collections.singletonList("ISO8601"), structure.getJodaTimestampFormats());
FieldStats messageFieldStats = structure.getFieldStats().get("message");
assertNotNull(messageFieldStats);
for (String statMessage : messageFieldStats.getTopHits().stream().map(m -> (String) m.get("value")).collect(Collectors.toList())) {
assertThat(structureFinder.getSampleMessages(), hasItem(statMessage));
}
}

public void testCreateConfigsGivenElasticsearchLogAndTimestampFieldOverride() throws Exception {
Expand Down Expand Up @@ -158,6 +168,11 @@ public void testCreateConfigsGivenElasticsearchLogAndTimestampFieldOverride() th
assertEquals("\\[%{TIMESTAMP_ISO8601:my_time}\\]\\[%{LOGLEVEL:loglevel} \\]\\[.*", structure.getGrokPattern());
assertEquals("my_time", structure.getTimestampField());
assertEquals(Collections.singletonList("ISO8601"), structure.getJodaTimestampFormats());
FieldStats messageFieldStats = structure.getFieldStats().get("message");
assertNotNull(messageFieldStats);
for (String statMessage : messageFieldStats.getTopHits().stream().map(m -> (String) m.get("value")).collect(Collectors.toList())) {
assertThat(structureFinder.getSampleMessages(), hasItem(statMessage));
}
}

public void testCreateConfigsGivenElasticsearchLogAndGrokPatternOverride() throws Exception {
Expand Down Expand Up @@ -191,6 +206,13 @@ public void testCreateConfigsGivenElasticsearchLogAndGrokPatternOverride() throw
"\\[%{JAVACLASS:class} *\\] \\[%{HOSTNAME:node}\\] %{JAVALOGMESSAGE:message}", structure.getGrokPattern());
assertEquals("timestamp", structure.getTimestampField());
assertEquals(Collections.singletonList("ISO8601"), structure.getJodaTimestampFormats());
FieldStats messageFieldStats = structure.getFieldStats().get("message");
assertNotNull(messageFieldStats);
for (String statMessage : messageFieldStats.getTopHits().stream().map(m -> (String) m.get("value")).collect(Collectors.toList())) {
// In this case the "message" field was output by the Grok pattern, so "message"
// at the end of the processing will _not_ contain a complete sample message
assertThat(structureFinder.getSampleMessages(), not(hasItem(statMessage)));
}
}

public void testCreateConfigsGivenElasticsearchLogAndImpossibleGrokPatternOverride() {
Expand Down